HazeFlow: Revisit Haze Physical Model as ODE and Non-Homogeneous Haze Generation for Real-World Dehazing [ICCV 2025]

Vapoursynth function to remove video distortions, turbulance, wobble, warp, heat haze, or similar

[NeurIPS2024 Spotlight] Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network

Real Scene Single Image Dehazing Network with Multi-Prior Guidance and Domain Transfer [IEEE TMM 2025]

[Pattern Recognition 2023] Physical Model and Image Translation Fused Network for Single-Image Dehazing

深圳大学金融科技学院2024-2025第一学期人工智能与机器学习课程第六组期末作业

The Official Implementation for "HAIR: Hypernetworks-based All-in-One Image Restoration".

The Official Implementation for paper "Chain-of-Restoration: Multi-Task Image Restoration Models are Zero-Shot Step-by-Step Universal Image Restorers".

Code for Blind Image Decomposition (BID) and Blind Image Decomposition network (BIDeN). ECCV, 2022.

Dehazing using multiscale(processing) dark channel prior

[ACCV22] Structure Representation Network and Uncertainty Feedback Learning for Dense Non-Uniform Fog Removal, https://arxiv.org/abs/2210.03061

This is the source code of PMS-Net: Robust Haze Removal Based on Patch Map for Single Images which has been published in CVPR 2019 Long Beach

This is the project page of our paper which has been published in ECCV 2020.

This repo is based on an Autoencoder model for image dehazing from different types of hazes like smog, smoke or fog or even in fire inicidents

Dataset and code of our AAAI2022 paper "Transmission-Guided Bayesian Generative Model for Smoke Segmentation"

In this Project, important algorithms such as Canny Edge Detection, Harris Corner Detection, Segmentation, and Dehazing are utilized. These algorithms perform operations like detecting edges and corners in images, segmenting different regions, and enhancing foggy or blurred images.

[NC2021] Prior guided conditional generative adversarial network for single image dehazing

How to use modern deep learning framework instead of tradition image digit process ?

[CVPR 2023] | RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priors

This is the source code of PMHLD-Patch-Map-Based-Hybrid-Learning-DehazeNet-for-Single-Image-Haze-Removal which has been accepted by IEEE Transaction on Image Processing 2020.